How to Use the Baseten MCP in Mastra AI

Q: How do I require approval before running a Baseten tool in Mastra AI?

Set requireToolApproval to true on your Mastra AI agent. This pauses the execution when the agent wants to call predict or modify your models until a human approves it.

Build resilient TypeScript workflows that run Baseten inferences and manage models automatically using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baseten MCP to Mastra AI

Create your Vinkius account to connect Baseten to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Baseten with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Baseten predictions inside Mastra AI pipelines

The `predict` tool executes serverless inferences using your deployed models on Baseten via our MCP Server. It takes raw inputs and returns predictions to your Mastra AI agent. Mastra AI wraps this tool in its workflow engine to handle inference timeouts. If a cold start delays the prediction, the agent triggers an exponential backoff retry to guarantee execution.

Automate model deployment checks

The `list_deployments` tool retrieves the running instances and active endpoints for your Baseten models. This gives your agent a snapshot of current capacity. Mastra AI uses this data to run conditional branches. If the agent detects zero active deployments, it executes a branch to trigger a cold-start prediction or notifies your team before running heavy workloads.

Verify workspace secrets before running Mastra AI steps

The `list_secrets` tool checks the names of the environment variables configured in your Baseten workspace over MCP. It returns the list of active keys without exposing their sensitive values. Mastra AI runs this check as a pre-flight step in your pipelines. The workflow halts and alerts an operator if a required API key is missing from your workspace.

Setup guide

Set up Baseten MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Baseten tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "baseten-mcp-client",
  servers: {
    "baseten-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Baseten Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Baseten tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Baseten transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Baseten. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Baseten now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Baseten MCP in Mastra AI

Initialize the MCP client with the Baseten server URL. Call `listTools` and spread the resulting tools directly into your Mastra agent configuration.

Yes, Mastra AI uses its built-in workflow engine to catch failures from the `predict` tool. It automatically retries the inference call using your configured backoff rules.

Set `requireToolApproval` to true on your Mastra AI agent. This pauses the execution when the agent wants to call `predict` or modify your models until a human approves it.

Yes, you can restrict the agent's access. It will only see the models returned by `list_models` and `get_model` that match its configured workspace permissions.

Your workspace secret names and inference inputs travel through an encrypted SSE or HTTP transport. The Vinkius sandbox executes the MCP server in an isolated, ephemeral environment, ensuring your proprietary model parameters never persist on disk.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript